Real-time semantic segmentation is the task of achieving computationally efficient semantic segmentation (while maintaining a base level of accuracy).
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks.
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints.
Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields.
#2 best model for Real-Time Semantic Segmentation on Cityscapes
We consider an important task of effective and efficient semantic image segmentation.
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots.
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Semantic segmentation requires both rich spatial information and sizeable receptive field.
#2 best model for Real-Time Semantic Segmentation on CamVid
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses.
#8 best model for Real-Time Semantic Segmentation on Cityscapes
It is shown that skip architecture in the decoding method provides the best compromise for the goal of real-time performance, while it provides adequate accuracy by utilizing higher resolution feature maps for a more accurate segmentation.